Robert TaFounder & CEO, Clarity · Building Hyper-Personalized Agents

I'm shipping the harness that turns a PM into a judge

22 Jul 2026 · 2 min

Watch on YouTube

1:46

In this presentation Robert Ta introduces the open‑source Clarity harness, a modular framework designed to augment product managers with AI agents that act as a “judge” over their work. The harness follows a philosophy of layered, domain‑specific and company‑wide harnesses, each exposing specialized agents. At the top sits the Clarity orchestrator, which coordinates an interview agent that captures raw input (e.g., meeting transcripts), a requirements synthesizer that extracts and structures product requirements, and a story‑writer agent that turns those requirements into user‑story artifacts. The workflow lets a product manager view the provenance of each artifact—seeing the original transcript, the diff from previous versions, and the full generated story—so they can approve, annotate, or request regeneration. The system also supports plugging in external agents (e.g., Cloud Code) via a skill orchestrator, enabling seamless scaling and reuse of services. The overall goal is to embed agents directly into the product‑development flow, provide transparent traceability of agent runs, and give product managers a “judge” interface to validate and improve AI‑generated outputs.

Chapters

If you're a product manager, this is how we're evolving our work. What I'm about to show you is our own Clarity harness that we're about to ship open source. And this harness takes the philosophy that every individual has their own individual harness. There should be domain-specific harnesses. There should also be department or company-wide harnesses. The whole thinking is if I'm a product manager, I'm going to have like a story writer agent. At the top, we have this Clarity orchestrator agent. I have this interview agent that captures input. I have like a requirements synthesizer agent. So I could like open these up in this harness. Harness and see a view where I could actually very easily see, oh, this was from this transcript. Hey, we should think about a way to scale this as services stuff. We pulled this, my story writer agent worked with the requirements synthesizer agent to pull from the transcript. What are the requirements and how do we write this as a story? And then you as the judge could be like, okay, this was quoted from here. What was the chain that got me here? This is the transcript. What did we add? What was the diff from before? What's the full artifact look like? Cool, that's the requirement. I could approve it, I could annotate it, I could say this requirement was too narrow. We should better specify broader. And I could save that and that saves in my Harness and then I could regenerate it. The idea is your agents that you're working with, like if you're working with Cloud Code, it's gonna spin up some agents. If you're working with your own agents, you're gonna point it to say, hey, like use the skill orchestrator, calls the agent, calls a skill. Kind of thing. So with a harness like this where you are in the flow of work, you're writing your stories, you're making your prototypes, blah, blah, blah. You have agents doing stuff. The idea is there are agent runs and you wanna know, did the input that I put in get me the expected output? And then how do I make that even better next time?